Differentiation between pulmonary cryptococcosis and lung adenocarcinoma based on intranodal and perinodal CT radiomics models
10.3969/j.issn.1002-1671.2024.10.006
- VernacularTitle:基于结节内及周围CT影像组学模型鉴别肺隐球菌病与肺腺癌
- Author:
Danni DONG
1
,
2
;
Xiaojun ZHOU
;
Qi DAI
;
Hai CHEN
;
Jianjun ZHENG
;
Jingfeng ZHANG
Author Information
1. 宁波大学医学部,浙江 宁波 315211
2. 宁波市第二医院放射科,浙江 宁波 315099
- Keywords:
pulmonary cryptococcosis;
lung adenocarcinoma;
radiomics
- From:
Journal of Practical Radiology
2024;40(10):1601-1605
- CountryChina
- Language:Chinese
-
Abstract:
Objective To investigate the value of CT radiomics models based on intranodal and perinodal in distinguishing pulmonary cryptococcosis(PC)from lung adenocarcinoma.Methods A total of 194 patients,including PC(n=94)and lung adenocarcinoma(n=100),confirmed by surgical or puncture pathology were analyzed retrospectively and randomly divided into training set and test set in a ratio of 7∶3.3D Slicer was used to delineate and extract the intranodal and perinodal volume of interest(VOI)radiomics features within a 5 mm range.The minimum redundancy maximum relevance(mRMR)and least absolute shrinkage and selection operator(LASSO)methods were used to dimensionality reduction.Statistically significant indicators were screened by one-way logistic regression and further incorporated into the multifactor logistic regression model.Support vector machine(SVM)was used to construct the intranodal image-based radiomics model,the perinodal image-based radiomics model,the intranodal-and-perinodal image-based radiomics model,and the combined model.The diagnostic efficacy of each model was evaluated by receiver operating characteristic(ROC)curve.Results In the test set,the area under the curve(AUC)of the clinical imaging model,the intranodal image-based radiomics model,the perinodal image-based radiomics model,the intranodal-and-perinodal image-based radiomics model,and the combined model were 0.84,0.88,0.85,0.90,and 0.94,respectively.Conclusion The combined model based on clinical imaging features,intranodal and perinodal radiomics features can improve the ability of differentiating PC from lung adenocarcinoma.
